Abstract
Automation of Radio Access Network (RAN) operation is a fundamental feature to manage sustainable and efficient Beyond Fifth-generation wireless (5G) networks, in the context of the Next Generation Self-Organizing Network (NG-SON) vision. Machine Learning (ML) is already identified as the key ingredient of this vision, with new standardized and open architectures, like Open-RAN (O-RAN), taking momentum. In this paper, we propose models based on single-task and Multi-Task Learning (MTL) paradigms to address two RAN use cases, handover management and initial Modulation and Coding Scheme (MCS) selection. Traditional handover schemes have the drawback of taking into account the quality of the signals from the serving, and the target cell, before the handover. Also, initial MCS at the start of the session and after a handover usually is handled conservatively. The proposed ML solutions allow to address these drawbacks by 1) considering the expected Quality of Experience (QoE) resulting from the decision of a target cell to handover, as the driving principle of the handover decision and 2) using the experience extracted from network data to make smarter initial MCS allocations. In this line, we implement a realistic cellular simulation scenario by incorporating coverage holes to build an extensive database to train and test the proposed models. The results show that the ML-based models outperform the 3rd Generation Partnership Project (3GPP) standardized handover and initial MCS selection approaches by improving the QoE of users resulting from a handover and the throughput obtained upon establishing a new connection with a network. Besides that, using the obtained results, this paper extensively discusses the merits of leveraging the MTL model to address different, but related multiple RAN functions because it allows reusing a common learning architecture for multiple RAN use cases, which provides significant implementation advantages.
Highlights
Mobile communications have experienced during the last decades an incredible evolution
We model the problem as a regression problem, where we aim to estimate the necessary time to download a file transmitted over a Transmission Control Protocol (TCP) transport, while the users move around in a realistic multi-cell scenario challenged by deep outage zones
To prove our MTL concept in the efficient RAN management domain, we selected two RAN use cases, 1) the HO management and 2) the selection of an initial MCS when User Equipment (UE) establish a new connection with a Generation Node B (gNB)
Summary
Mobile communications have experienced during the last decades an incredible evolution. This approach can significantly reduce the implementation and computational complexity of the learning architectures To prove this concept, we propose to target, without loss of generality, two RAN use cases: 1) HO management and 2) the selection of the optimal initial Modulation and Coding Scheme (MCS). We propose to target, without loss of generality, two RAN use cases: 1) HO management and 2) the selection of the optimal initial Modulation and Coding Scheme (MCS) We address both the use cases, first through single-task individual and through multi-task shared models. We propose a second incremental MTL scheme, based on the continual learning paradigm [14], where the training database is not built beforehand, but a new task can be incorporated separately while previous task knowledge is preserved This approach is much more flexible and adequate for real networks and provides clear implementation advantages [15].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
